Study on sorting technology of fresh tea leaves based on convolutional neural network model

Abstract

A convolutional neural network (CNN) model was designed based on computer vision technology, given the difficulty in accurately subdividing tea leaves traditional sorting methods. The model has three convolutional layers, two pooling layers, and one fully connected layer. Through the training and testing of the real shot Huoshanhuangya teas image, the correct rate of the model to identify Huoshanhuangya teas reached 95.3%. The experimental results show that the fresh tea leaves sorting technology based on the convolutional neural network model solves the problem of relying on manual sorting and mixing of different types of fresh tea, and improves the quality and value of Huoshanhuangya teas.